IJRCIT- International Journal of Research in Computer & Information Technology

Archives of International Journal of Research in Computer & Information Technology(IJRCIT)

Volume 8 Issue 1 December 2022

1. Analysis o f Synthetic Video for Deepfake Video Detection Using Deep Learning

AUTHOR NAME : Bhushan Wakode, Mukesh Poundekar

ABSTRACT : Deepfake videos generated using advanced deep learning techniques such as Generative Adversarial Networks have become increasingly realistic and difficult to detect, posing serious threats to digital media authenticity, social security, and information integrity. This paper presents a deep learning-based framework for deepfake video detection that focuses on facial feature analysis and frame-level classification. The proposed methodology includes video frame extraction, face detection, face cropping, dataset preparation, and deep learning-based feature extraction and classification. The system is designed to distinguish between real and fake videos by learning discriminative spatial features from facial regions. The dataset is divided into training and testing sets to evaluate the performance of the model. The effectiveness of the proposed deepfake detection framework is evaluated using performance metrics such as accuracy, precision, recall, F1-score, and ROC-AUC. The experimental results demonstrate that the proposed system can effectively identify deepfake videos and provides a reliable approach for detecting manipulated video content. The proposed method contributes to the development of automated deepfake detection systems for improving digital media security and forensic analysis.

Download